< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 1940 in Layer 28

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')



Text #0

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.8187. Min Act: -0.1700

Data Index: 449989 (Open Web Text)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.5062. Min Act: -0.1700

Data Index: 8085090 (Open Web Text)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.4437. Min Act: -0.1700

Data Index: 8049981 (Open Web Text)

Max Activating Token Index: 461

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.4437. Min Act: -0.1700

Data Index: 2585857 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.1937. Min Act: -0.1700

Data Index: 6486398 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.2562. Min Act: -0.1700

Data Index: 2990276 (Open Web Text)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.1937. Min Act: -0.1700

Data Index: 7311258 (Open Web Text)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.1937. Min Act: -0.1700

Data Index: 5611509 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.0687. Min Act: -0.1700

Data Index: 57024 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.0062. Min Act: -0.1700

Data Index: 4336472 (Open Web Text)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.0062. Min Act: -0.1700

Data Index: 4239120 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.0062. Min Act: -0.1700

Data Index: 4551520 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.0062. Min Act: -0.1700

Data Index: 4175402 (Open Web Text)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.8187. Min Range: -10.8187

Max Act: 10.0062. Min Act: -0.1700

Data Index: 5963615 (Open Web Text)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.8187. Min Range: -10.8187

Max Act: 9.9437. Min Act: -0.1700

Data Index: 4582226 (Open Web Text)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.8187. Min Range: -10.8187

Max Act: 9.9437. Min Act: -0.1700

Data Index: 1884455 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.8187. Min Range: -10.8187

Max Act: 9.9437. Min Act: -0.1700

Data Index: 3101713 (Open Web Text)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.8187. Min Range: -10.8187

Max Act: 9.9437. Min Act: -0.1700

Data Index: 5630795 (Open Web Text)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.8187. Min Range: -10.8187

Max Act: 9.9437. Min Act: -0.1700

Data Index: 7793562 (Open Web Text)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.8187. Min Range: -10.8187

Max Act: 9.9437. Min Act: -0.1700

Data Index: 2659918 (Open Web Text)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #19